Speak While You Think: Streaming Speech Synthesis During Text Generation.
Avihu DekelSlava ShechtmanRaul FernandezDavid HawsZvi KonsRon HooryPublished in: ICASSP (2024)
Keyphrases
- speech synthesis
- text generation
- speech recognition
- natural language generation
- text to speech
- natural language
- vocal tract
- data streams
- prosodic features
- real time streaming
- video streaming
- real time
- speech corpus
- streaming data
- dialogue system
- theorem prover
- language model
- natural language processing
- hidden markov models
- expert systems
- streaming video
- streaming media
- multi agent systems
- feature extraction